Soybean seed vigor discrimination by using infrared spectroscopy and machine learning algorithms

Evaluating the effectiveness of coagulation-flocculation treatment on a wastewater from the moroccan leather tanning industry : An ecological approach

The removal of pollutants from tannery wastewaters, which is renowned for its substantial volumes, intricate composition, and considerable hazards to human health and the environment, is a prominent research area in the field of water treatment. The aim of this study is to employ a bio-coagulant derived from Parkinsonia aculeata seeds and a bio-flocculant derived from Hibiscus esculentus to minimise the concentration of pollutants in the combined wastewater originating from tanneries. In the course of the research, a thorough physicochemical analysis of the coagulating and flocculating agents, Parkinsonia aculeata (PA) and Hibiscus esculentus (HE), was performed using techniques such as XRD (X-ray diffraction), FTIR (Fourier-transform infrared spectroscopy), and SEM-EDS (scanning electron microscopy-energy dispersive X-ray spectroscopy). This analysis aimed to determine the composition and characteristics of these biomasses. Subsequently, a comprehensive overview was conducted to summarize the various factors that influence the treatment of tannery wastewater through coagulation/flocculation. This was accomplished by manipulating the target factors and observing their impact on the removal of specific physicochemical parameters such as chemical oxygen demand (COD), electrical conductivity (EC), total chromium (Cr) and Optical density (OD). The variables that were established include pH, dosage of coagulant and flocculant, as well as the speed and duration of agitation in both the fast and slow mixing stages. The experiments were carried out while taking into account the optimal parameters, leading to the near-complete removal of all analyzed pollutants. The optimal requirements for the Parkinsonia aculeata-Hibiscus esculentus Coagulation Flocculation System involve adjusting the pH to 8, choosing concentrations of approximately 1.25 g L-1 and 0.6 g L-1 for the coagulant and flocculant respectively, maintaining a fast speed of 170 rpm for 3 min while keeping the slow agitation at around 30 rpm for 20 min. The removal rates achieved after treating tannery wastewater using the PA-HE coagulant-flocculant combination demonstrate high efficacy, with values reaching approximately 100% for TSS, 98.71% for BOD5, 99.93% for COD, 98.88% for NH4+, 98.21% for NO3-, 90.32% for NO2-, 93.13% for SO42-, 95.44% for PO43-, 96.08% for OD and 60% for total chromium. These results indicate the successful removal of a wide range of pollutants from tannery wastewater through the PA-HE treatment method. In predicting the CF treatment approach, PCA has been employed to preprocess the input data and determine the key variables that impact the process. This can streamline the modeling process and enhance the precision of the predictions.

Turning chaotic sample group clusterization into organized ones by feature selection: Application on photodiagnosis of Brucella abortus serological test

Bovine brucellosis diagnosis is a major problem to be solved; the disease has a tremendous economic impact with significant losses in meat and dairy products, besides the fact that it can be transmitted to humans. The sanitary measures instituted in Brazil are based on disease control through diagnosis, animal sacrifice, and vaccination. Although the currently available diagnostic tests show suitable quality parameters, they are time-consuming, and the incidence of false-positive and/or false-negative results is still observed, hindering effective disease control. The development of a low-cost, fast, and accurate brucellosis diagnosis test remains a need for proper sanitary measures at a large-scale analysis. In this context, spectroscopy techniques associated with machine learning tools have shown great potential for use in diagnostic tests. In this study, bovine blood serum was investigated by UV-vis spectroscopy and machine learning algorithms to build a prediction model for Brucella abortus diagnosis. Here we first pre-treated the UV raw data by using Standard Normal Deviate method to remove baseline deviation, then apply principal component analysis - a clustering method - to observe the group formation tendency; the first results showed no clustering tendency with a messy sample score distribution, then we properly select the main principal components to improve clusterization. Finally, by using machine learning algorithms (SVM and KNN), the predicting models achieved a 92.5% overall accuracy. The present methodology provides a test result in an average time of 5 min, while the standard diagnosis, with the screening and confirmatory tests, can take up to 48 h. The present result demonstrates the method's viability for diagnosing bovine brucellosis, which can significantly contribute to disease control programs in Brazil and other countries.

Photoacoustic Spectroscopy Combined with Integrated Learning to Identify Soybean Oil with Different Frying Durations

Soybean oil produces harmful substances after long durations of frying. A rapid and nondestructive identification approach for soybean oil was proposed based on photoacoustic spectroscopy and stacking integrated learning. Firstly, a self-designed photoacoustic spectrometer was built for spectral data collection of soybean oil with various frying times. At the same time, the actual free fatty acid content and acid value in soybean oil were measured by the traditional titration experiment, which were the basis for soybean oil quality detection. Next, to eliminate the influence of noise, the spectrum from 1150 cm^-1 to 3450 cm^-1 was selected to remove noise by ensemble empirical mode decomposition. Then three dimensionality reduction methods of principal component analysis, successive projection algorithm, and competitive adaptive reweighting algorithm were used to reduce the dimension of spectral information to extract the characteristic wavelength. Finally, an integrated model with three weak classifications was used for soybean oil detection by stacking integrated learning. The results showed that three obvious absorption peaks existed at 1747 cm^-1, 2858 cm^-1, and 2927 cm^-1 for soluble sugars and unsaturated oils, and the model based on stacking integrated learning could improve the classification accuracy from 0.9499 to 0.9846. The results prove that photoacoustic spectroscopy has a good detection ability for edible oil quality detection.

Algorithm and hyperparameter optimizations for hetero-device classification by near-infrared spectra of falsified and substandard amoxicillin capsules

In this work, we optimized classification algorithms and the hyperparameters for screening falsified and substandard amoxicillin capsules. The distribution of low-quality medical products is a serious problem, especially in low- and middle-income countries. Near-infrared (NIR) spectroscopy has been proposed as the first choice for a screening device. However, preparation of the reference library for the classification training is a highly difficult process. We herein propose a hetero-device classification between training and test devices. In this proposal, Fourier-transform NIR spectrometer and portable wavelength dispersive NIR spectrometer were used as training and test devices, respectively. As the classifier candidates, we examined 13 algorithms and selected 8. We then optimized the hyperparameters for these classifiers by the grid search and cross validation methods. In the final analysis, few classifiers were found to give acceptable prediction results by the hetero-device classification. When using these methods, it is crucial to examine the results by the classification probability, due to the trade-off between sensitivity and specificity. Finally, we suggest that k-nearest neighbors, extra trees, and gradient boosting classifiers are the optimal algorithms with high classification probability for the substandard and falsified amoxicillin capsules.

Laser-Induced Breakdown Spectroscopy Associated with the Design of Experiments and Machine Learning for Discrimination of Brachiaria brizantha Seed Vigor

Laser-induced breakdown spectroscopy (LIBS) associated with machine learning algorithms (ML) was used to evaluate the Brachiaria seed physiological quality by discriminating the high and low vigor seeds. A 2³ factorial design was used to optimize the LIBS experimental parameters for spectral analysis. A total of 120 samples from two distinct cultivars of Brachiaria brizantha seeds exhibiting high vigor (HV) and low vigor (LV) in standard tests were studied. The raw LIBS spectra were normalized and submitted to outlier verification, previously to the reduction data dimensionality from principal component analysis. Supervised machine learning algorithm parameters were chosen by leave-one-out cross-validation in the test samples, and it was tested by external validation using a new set of data. The overall accuracy in external validation achieved 100% for HV and LV discrimination, regardless of the cultivar or the classification algorithm.

Soybean processing wastes and their potential in the generation of high value added products

Soybean and its derivatives are rich sources of nutrients and bioactive compounds with antioxidant properties, however, the wastes with high nutritional value are discarded by the industry. This study aimed to evaluate centesimal composition, microbial safety and antioxidant activity of soybean processing wastes (okara and okara flour) and soymilk. High fiber, carbohydrate, energy and lipids contents were found. Antioxidant activity by spectrophotometric and Electron Paramagnetic Resonance assays showed values for soybean (72.4% and 83.5%), okara (9.6% and 7.7%), okara flour (30.7% and 11.5%) and soymilk (28.4% and 36.5%). The total phenolic content was an average of 3.33 mg of gallic acid equivalent.g-1. Infrared spectra revealed no significant changes in the absorption bands, guaranteeing non-alteration in the compounds composition after processing. Microbiological assays indicated that soybean derivatives are safe for consumption. These results reinforce that these wastes contain bioactive compounds of interest with great potential to generate high value added products.

FTIR spectroscopy with machine learning: A new approach to animal DNA polymorphism screening

Technological advances in recent decades, especially in molecular genetics, have enabled the detection of genetic DNA markers associated with productive characteristics in animals. However, the prospection of polymorphisms based on DNA sequencing is still expensive for the reality of many food-producing regions around the world, such as Brazil, demanding more accessible prospecting methods. In the present study, the Fourier transform infrared spectroscopy (FTIR) and machine learning algorithms were used to identify single nucleotide polymorphism (SNP) in animal DNA. The fragments of bovine DNA with well-known polymorphisms were used as a model. The DNA fragments were produced and genotyped by PCR-RFLP and classified according to the genotype (homozygous or heterozygous). FTIR spectra of DNA fragments were analyzed by principal component analysis (PCA) and machine learning algorithms. The best results exhibited 75-95% accuracy in the classification of bovine genotypes. Therefore, FTIR spectroscopy and multivariate analysis can be used as an alternative tool for prospecting polymorphisms in animal DNA. The method can contribute with studies to identify genetic markers associated with animal production and indirectly with food production itself, and reduce pressure on available natural resources.

A new strategy for canine visceral leishmaniasis diagnosis based on FTIR spectroscopy and machine learning

Visceral leishmaniasis is a neglected disease caused by protozoan parasites of the genus Leishmania. The successful control of the disease depends on its accurate and early diagnosis, which is usually made by combining clinical symptoms with laboratory tests such as serological, parasitological, and molecular tests. However, early diagnosis based on serological tests may exhibit low accuracy due to lack of specificity caused by cross-reactivities with other pathogens, and sensitivity issues related, among other reasons, to disease stage, leading to misdiagnosis. In this study was investigated the use of mid-infrared spectroscopy and multivariate analysis to perform a fast, accurate, and easy canine visceral leishmaniasis diagnosis. Canine blood sera of 20 noninfected, 20 Leishmania infantum, and eight Trypanosoma evansi infected dogs were studied. The data demonstrate that principal component analysis with machine learning algorithms achieved an overall accuracy above 85% in the diagnosis.

Intraspecific differentiation of sandflies specimens by optical spectroscopy and multivariate analysis

Lutzomyia longipalpis and Lutzomyia cruzi are the main sandflies species involved in the transmission of Leishmania infantum protozoan in Brazil. The morphological characteristics can be used for species identification of males specimens, while females are indistinguishable. Although, sandflies identification is essential to understand vectorial capacity, and susceptibility to infectious agents or insecticides, there is a lack of new strategies for specimen identification. In this study, Fourier transform infrared photoacoustic spectroscopy combined with multivariate analysis identified intraspecific differences between Lutzomyia populations. Successfully group clustering was achieved by principal component analysis. The main differences observed can be related to the protein content of the specimens. A classification with 100% accuracy was obtained using machine learning approach, allowing the identification of sandflies specimens.